Vous êtes sur la page 1sur 4

(IJCSIS) International Journal of Computer Science and Information Security,

Vol. 8, No.4, 2010

Media Streaming using Multiple Description Coding


in Overlay Networks
Sachin Yadav Ranjeeta Yadav Shailendra Mishra
Department of CSE Department of ECE Department of CSE
SGIT College of Engineering SGIT College of Engineering Kumaon Engineering College
Ghaziabad, India Ghaziabad, India Dwarahat, India
sac.yaduvanshi@gmail.com ranjeeta29@gmail.com skmishra1@gmail.com

Abstract—In this paper we examine the performance of two high dynamic system, where clients can come and leave
types of Overlay networks i.e. Peer-to-Peer (P2P) & Content suddenly without any prior knowledge or guarantees.
Delivery Network (CDN) media streaming using Multiple Today’s video streaming systems are mostly based on the
Description Coding (MDC). In both the approaches many servers client server model of Content Delivery Networks (CDN)
simultaneously serve one requesting client with complementary which leads to several problems. The most important ones are:
descriptions. This approach improves reliability and decreases
the data rate a server has to provide. We have implemented both 1. Flash Crowd: Large numbers of streaming servers are not
approaches in the ns-2 network simulator. The experimental able to feed more than a few hundred streaming sessions
results indicate that the performance of Multiple Description simultaneously [2].
Coding-based media streaming in case of P2P network is better
than CDN. 2. Bandwidth cost: It can be a significant problem to the
content provider. In contrast, these costs are shared by
Keywords- MDC; CDN; Video Streaming; P2P; Overlay every participant in the P2P streaming network.
Network 3. Single Point of failure: Like any client-server model, the
I. INTRODUCTION server is the single point of failure.
Media streaming received lot of attention in the past few P2P networks offer characteristics and possibilities which
years. As a consequence, live and on-demand media streaming cannot be provided by CDNs as proposed in [10]. As we show
is today widely used to stream TV & radio channels, TV in this work, the performance of media streaming can he better
shows, or arbitrary audio & video media. During this time in a P2P network, although the probability that one stream
several approaches have been devised to tackle the media- breaks is higher [13] [4]. The reason for this is that the
streaming problem. The first one is to use a client-server replication rate of the video streams in a P2P network is
model, where a single server is the media provider and typically significantly higher than in a CDN, due to the large
multiple clients are the media consumers. The second one is to number of participating hosts. In Gnutella for example, every
use a peer-to-peer approach where the clients help the server peer shares an average of 500 files [15] and many peers host
in delivering the media content by having the roles of the same file.
consumers and providers at the same time.
Both schemes have their advantages and
disadvantages. The client-server approach has the advantage
that the client receives the content directly from the server
with the minimum delay but at the cost of overwhelming the
server in particular situations (for instance at high rate hours:
e.g. football / basketball games etc). As a result, the server’s
bandwidth can quickly become a bottleneck in the system due
to the large number of client requests. On the other hand, in
the peer-to-peer approach algorithms are devised to multicast
the content between clients. In this case the clients have an
active role in distributing the media content to other clients
and thus remove the pressure from the server node. In this
way, scaling the system functionality to a large number of
consumers becomes a reality. However, this solution has its
drawbacks too. Specifically, these algorithms have to tackle a Figure 1: Distributed video streaming using multiple
description coding in a P2P network. Peer P1 is

136 http://sites.google.com/site/ijcsis/
ISSN 1947-5500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No.4, 2010
simultaneously serve by the closest available peers P6 & P3 In this paper, we are concerned with video streaming, which
with descriptions D1 & D2 respectively. refers to real-time transmission of stored video. There are two
Using MDC in a P2P streaming scenario is illustrated in modes for transmission of stored video over the Internet,
Figure 1. Peer p1 wants to receive video file S which is namely the download mode and the streaming mode (i.e.,
available in the MDC format on p3, p5 and p6. In this example video streaming). In streaming mode, the video content need
the video is encoded using two descriptions D1 & D2. Peers not be downloaded in full, but is being played out while parts
p3 and p6 are chosen based on the distance from server to the of the content are being received and decoded. Due to its real-
receiver, and they simultaneously serve the video file S, each time nature, video streaming typically has bandwidth, delay
one providing a complementary description. If both the and loss requirements. However, the current best-effort
Internet does not offer any quality of service (QoS) guarantees
descriptions are received at the receiving peer p1, it will
to streaming video over the Internet. In addition, for multicast,
experience the highest quality. If any of the descriptions are it is difficult to efficiently support multicast video while
affected by packet loss or excessive delay, the receiver can providing service flexibility to meet a wide range of QoS
still decode and display video S but at the expense of a requirements from the users. Thus, designing mechanisms and
degradation of the quality, as the descriptions are protocols for Internet streaming video poses many challenges.
independently decodable. It has been demonstrated in [16] that using MDC in
combination with packet path diversity significantly improves
II. MULTIPLE DESCRIPTION VIDEO CODING the robustness of a real-time video application.

Multiple Description coding (MDC) is a coding


technique that fragments a single media stream into n sub
streams (n ≥ 2) referred to as descriptions. The packets of each
description are routed over multiple, (partially) disjoint paths.
In order to decode the media stream, any description can be
used, however, the quality improves with the number of
descriptions received in parallel. The idea of MDC is to
provide error resilience to media streams. Since an arbitrary
subset of descriptions can be used to decode the original
stream, network congestion or packet loss — which are
common in best-effort networks such as the Internet — will
not interrupt the stream but only cause a (temporary) loss of
quality. The quality of a stream can be expected to be roughly
proportional to data rate sustained by the receiver. Figure 3: Architecture for video streaming.

In Figure 3, raw video and audio data are pre-compressed


by video compression and audio compression algorithms and
then saved in storage devices. Upon the client’s request, a
streaming server retrieves compressed video/audio data from
storage devices and then the application-layer QoS control
module adapts the video/audio bit-streams according to the
network status and QoS requirements. After the adaptation, the
Figure 2: MD source coding with two channels and three transport protocols packetize the compressed bit-streams and
receivers. The general case has M channels and 2M−1 receivers. send the video/audio packets to the Internet. Packets may be
dropped or experience excessive delay inside the Internet due
This property makes MDC highly suitable for lossy packet to congestion. To improve the quality of video/audio
networks where there is no prioritization among the packets. transmission, continuous media distribution services (e.g.,
The principle of MDC encoding/decoding is illustrated in caching) are deployed in the Internet. For packets that are
figure 2. For a general overview on Multiple Description successfully delivered to the receiver, they first pass through
Coding (MDC) refer to [1]. the transport layers and are then processed by the application
layer before being decoded at the video/audio decoder. To
III. VIDEO STREAMING OVER INTERNET achieve synchronization between video and audio
Media streaming systems are distinct from the file sharing presentations, media synchronization mechanisms are
systems [11], in which a client has to download the entire file required. From Figure 3, it can be seen that the six areas are
before using it. Real-time multimedia, as the name implies, closely related and they are coherent constituents of the video
has timing constraints. For example, audio and video data streaming architecture.
must be played out continuously. If the data does not arrive in
time, the play out process will pause, which is annoying to IV. MODELLING
human ears and eyes. Real-time transport of live video or We use the following methodologies in our simulations to
stored video is the predominant part of real-time multimedia. reflect the real-world network situations.

137 http://sites.google.com/site/ijcsis/
ISSN 1947-5500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No.4, 2010
1. Modeling Availability in P2P Networks V. RESULTS
We implemented both the P2P and CDN approaches
In P2P networks, peer and content availability poses a within the Network Simulator ns-2 [8]. The topology was
challenging problem to be solved. Availability of a peer in a created using the GT-ITM topology generation tool with the
P2P network is quite unpredictable, depending primarily on transit-stub model, having 100 nodes. A video file of 1 minute
human presence. In our experiments we model peer duration, having a data-rate of 100 Kbit/s was selected for all
availability as a 2 state markov process, having the states ON the simulations. Each packet contains 1000 bytes. In both the
and OFF. The average lifetime of a peer in a Gnutella network CDN and P2P based systems, there is one new request every
is found to be about 30 minutes [14]. For our experiments we second, originating from an arbitrary node. In P2P network,
take a Gaussian distribution of ON time, which has a mean of the file is streamed from two closest available peer nodes with
30 minutes. To model the availability of content among the complementary descriptions, whereas in CDN, the same is
peers, we randomly choose peers having a particular media served by two closest CDN servers. It was assumed that a peer
file. We vary the percentage of peers having the file from 5% can serve only one request at one time, while a CDN server
to 50%. can serve a maximum of 200 streams simultaneously.

2. Server Placement in CDN

The server placement problem addresses how to optimally


place a number of servers in order to maximize the quality at
the end user. In our experiments we varied the number of
servers to obtain measurement of Quality of Service, such as
packet loss and response time. For a particular number of
servers, we placed the servers randomly in the network and
measured the average round-trip-time from each user to the
servers. We performed this random placement 10 times and
chose the one yielding the smallest average round-trip-time.

3. Server Selection in P2P and CDN Network

The server selection problem addresses how to optimally


choose a pair of servers to get complementary descriptions in
order to maximize the perceived quality at the receiver. As
described in [10] Apostolopoulos proposed a path diversity
model which requires the knowledge of network topology, Figure 4: Performance of P2P and CDN networks using MDC:
including knowledge of joint and disjoint links, and loss (top) packet loss rate varies with varying number of CDN
characteristics for each link. In our experiments we simply servers and content availability in p2p network. (middle)
choose the closest two servers for each client request. For P2P number of decodable frames increases with increasing number
case, we choose the closest two serving peers having the of servers and availability. (bottom) average response times
required content. for P2P and CDN.

Figure 4 shows the results obtained through simulations. Three


4. Content Distribution across Servers in CDN performance parameters, namely the rate of packet loss,
number of non-decodable frames and the average response
This problem addresses how to optimally distribute the time, i.e. the time to receive the first video packet after the
Multiple Description streams in an existing set of servers. In request has been sent, are compared for P2P and CDN
this paper we assume that all the CDN servers contain both the networks. For the count of non-decodable frames, it is
descriptions, which simplifies the server selection problem by assumed that the descriptions contain an Intra frame once in
merely choosing the two closest servers. every second, and in case of a packet loss for the P-frames, all
the subsequent frames become non-decodable, until the next I-
frame is received. Because of MDC coding, the receiver can
5. Network Load still view with a reduced frame rate, unless both the
descriptions are corrupted simultaneously. This is shown in
To simulate the network load, we created random TCP figure 5, where description s1 contains a packet loss, but s2 is
connections originating from arbitrary nodes, on the average 3 received error-free. The receiver can view with ½ the original
new connections per second, each connection lasting for 1 frame rate until the next I-frame is received in s1.
minute.

138 http://sites.google.com/site/ijcsis/
ISSN 1947-5500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No.4, 2010
The simulation results indicate that the performance of a P2P [4] S. Saroiu, P. K. Gummadi, and S. D. Gribble, ―A measurement study of
peer-to-peer file sharing systems‖. In Proceedings of Multimedia
network is comparable to that of a CDN, even at the high Computing and Networking (MMCN), Jan. 2002.
unavailability of peers and content in the p2p network. [5] T. Nguyen and A. Zakhor, ―Distributed VideoStreaming‖, Multimedia
Computing and Networking 2002, Multimedia Conference, Jan 2002.
[6] Borella, M. S., D. Swider, S. Uludag, and G. B. Brewster, ―Internet
Packet Loss: Measurement and Implications for End-to- End QoS‖, in
Proceedings of the International Conference on Parallel Processing
(1998).
[7] F. M. Cuenca-Acuna, R. P. Martin, T. D. Nguyen. ―Autonomous
Replication for High Availability in Unstructured P2P Systems‖,
Technical Report DCS-TR-509, Department of Computer Science,
Figure 5: Impact of packet loss in MDC-based video Rutgers University. April 2003.
streaming. Only stream s2 can be decoded completely. s1 is [8] The Network Simulator, http://www.isi.edu/nsnam/ns/
affected by packet loss and lead to locally reduced frame rate [9] J. Kangasharju, K.W. Ross, D. Turner, ―Adaptive Replication and
of the reconstructed video. Replacement in P2P Caches‖, 2002. working paper.
[10] J. Apostolopoulos, T. Wong, W. Tan, S. Wee, ―On Multiple Description
VI. RELATED WORK Streaming with Content Delivery Networks‖, IEEE INFOCOM, June
2002.
[11] D. Xu, M. Hefeeda, S. Hambrusch, and B. Bhargava. ―On peer-to-peer
Peer-to-peer based media streaming approaches using media streaming.‖ In Proc. of IEEE ICDCS, Vienna, Austria, July 2002.
multiple serving hosts have been proposed in [12] and [5]. In [12] M. Hefeeda, B. Bhargava ―On-Demand Media Streaming Over the
[16] MDC-based distributed video streaming has been Internet‖, CERIAS TR 2002- 20, Purdue University, June 2002.
proposed for content delivery networks. Our work is inspired [13] R. Baghwan, S. Savage, G, M. Voelker. ―Understanding Availability‖.
by this work and we use the same multiple description In Proceedings of the International Workshop on Peer-to-Peer Systems
encoding technique for a P2P network. (IPTPS). February 2003.
[14] E. Adar, B. Huberman. ―Free Riding on Gnutella‖, First Monday, 5(10).
October 2000.
[15] J. Chu, K. Labonte, B. N. Levine, ―Availability and locality
VII. CONCLUSION measurements of peer-to-peer file systems,‖ in ITCom: Scalability and
Traffic Control in IP Networks, Proceedings of SPIE. vol. 4868, Jul.
2002.
In this paper we presented a performance comparison of
[16] J. G. Apostolopoulos, ―Reliable video communication over lossy packet
P2P media streaming with CDN – based media streaming, networks using multiple state encoding and path diversity‖, VCIP,
both employing MDC. The P2P approach takes advantage of January 2001.
multiple supplying peers to combat the inherent limitations of
the P2P network and the best effort Internet. The media AUTHORS PROFILE
content is encoded using a multiple description encoder which
allows realizing distributed streaming from more than one Sachin Yadav received his Bachelors in Computer Engineering from Pune
peer. In the final paper we plan to also provide experimental University in 2001. He is working currently as a Associate Prof & Head for
results on video dispersion, i.e. the time it takes to be able to the computer science department in SGIT, Ghaziabad and is pursuing his PhD
satisfy a large number of streaming requests for a new video from the Uttarakhand Technical University, Dehradun.
that is injected into the network, for both the P2P and CDN
Ranjeeta Yadav received her Bachelors in Electronics & Communication
network. Engineering from Uttar Pradesh Technical University in 2004. She received
her M.Tech in signal processing from Delhi University in 2009. She is
REFERENCES working currently as an Assistant Prof in Electronics & Communication
Engineering department in SGIT, Ghaziabad.
[1] V. K. Goyal. ―Multiple Description Coding: Compression Meets the
Network‖, IEEE Signal Processing Magazine, vol. 18, n.5, page(s) 74 – Shailendra Mishra got his Master degree from MNNIT, Allahabad and Ph.D
94. September 2001. in Computer Science & Engineering from Gurukul Kangri University,
Haridwar. He is working currently as a Prof & Head for the Computer Science
[2] Tyron Stading, Petros Maniatis, Mary Baker, ―Peer-to-Peer Caching department in KEC, Dwarahat. He published several research papers in
Schemes to Address Flash Crowds‖, 1st International Peer To Peer international journals and international conferences.
Systems Workshop (IPTPS) 2002.
[3] V. Padmanabhan, H. Wang, P. Chou, and K. Sripanidkulchai.
―Distributing streaming media content using cooperative networking.‖ In
Proc of NOSSDAV’02, Miami Beach, FL, USA, May 2002.

139 http://sites.google.com/site/ijcsis/
ISSN 1947-5500